ReMark: Receptive Field based Spatial WaterMark Embedding Optimization using Deep Network
This work addresses copyright protection for digital media creators and distributors, but it appears incremental as it builds on existing deep learning methods for watermarking.
The paper tackled the problem of embedding imperceptible watermarks in digital media for copyright protection by proposing a deep learning architecture that correlates watermark dimensions with receptive field sizes, resulting in improved robustness and image quality, with extensive evaluations showing effectiveness against common distortions including collusive ones.
Watermarking is one of the most important copyright protection tools for digital media. The most challenging type of watermarking is the imperceptible one, which embeds identifying information in the data while retaining the latter's original quality. To fulfill its purpose, watermarks need to withstand various distortions whose goal is to damage their integrity. In this study, we investigate a novel deep learning-based architecture for embedding imperceptible watermarks. The key insight guiding our architecture design is the need to correlate the dimensions of our watermarks with the sizes of receptive fields (RF) of modules of our architecture. This adaptation makes our watermarks more robust, while also enabling us to generate them in a way that better maintains image quality. Extensive evaluations on a wide variety of distortions show that the proposed method is robust against most common distortions on watermarks including collusive distortion.